Browsing by Author "Chumachenko, Olena"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Hybrid neural network optimization system based on ant algorithms
    (National Aviation University, 2020-07-06) Sineglazov, Victor; Chumachenko, Olena; Omelchenko, Dmytro; Синєглазов, Віктор Михайлович; Чумаченко, Олена Іллівна; Омельченко, Дмитро Валерійович
    The ant multi-criteria algorithm for feed forward neural networks training is proposed. It is used two criteria: the error of generalization and complexity. It is represented a review of neural network learning using swarm algorithms. As a result of training it is determined a structure of neural network (a number of layers and neurons in then) and the values of weight coefficients and biases. Modification of well-known algorithms consists in using the concept of Pareto optimality. It is done the research of proposed algorithm on the example of multilayer perceptron for the approximation problem solution.
  • Thumbnail Image
    Item
    Semi-controlled learning in information processing problems
    (National Aviation University, 2022-01-05) Sineglazov, Victor; Синєглазов, Віктор Михайлович; Chumachenko, Olena; Чумаченко, Олена Іллівна; Heilyk, Eduard; Хейлик, Едуард Володимирович
    The article substantiates the need for further research of known methods and the development of new methods of machine learning – semi-supervized learning. It is shown that knowledge of the probability distribution density of the initial data obtained using unlabeled data should carry information useful for deriving the conditional probability distribution density of labels and input data. If this is not the case, semi-supervised learning will not provide any improvement over supervised learning. It may even happen that the use of unlabeled data reduces the accuracy of the prediction. For semi-supervised learning to work, certain assumptions must hold, namely: the semi-supervised smoothness assumption, the clustering assumption (low-density partitioning), and the manifold assumption. A new hybrid semi-supervised learning algorithm using the label propagation method has been developed. An example of using the proposed algorithm is given.